Skip to Main Content
HBS Home
  • About
  • Academic Programs
  • Alumni
  • Faculty & Research
  • Baker Library
  • Giving
  • Harvard Business Review
  • Initiatives
  • News
  • Recruit
  • Map / Directions
Working Knowledge
Business Research for Business Leaders
  • Browse All Articles
  • Popular Articles
  • Cold Call Podcasts
  • About Us
  • Leadership
  • Marketing
  • Finance
  • Management
  • Entrepreneurship
  • All Topics...
  • Topics
    • COVID-19
    • Entrepreneurship
    • Finance
    • Gender
    • Globalization
    • Leadership
    • Management
    • Negotiation
    • Social Enterprise
    • Strategy
  • Sections
    • Book
    • Cold Call Podcast
    • HBS Case
    • In Practice
    • Lessons from the Classroom
    • Op-Ed
    • Research & Ideas
    • Research Event
    • Sharpening Your Skills
    • What Do You Think?
    • Working Paper Summaries
  • Browse All
    • COVID-19 Business Impact Center
      COVID-19 Business Impact Center
      Developing Theory Using Machine Learning Methods
      08 Oct 2018Working Paper Summaries

      Developing Theory Using Machine Learning Methods

      by Prithwiraj Choudhury, Ryan Allen, and Michael G. Endres
      This paper provides a step-by-step roadmap for using machine learning (ML) techniques to explore novel and robust patterns in data. It introduces management researchers to a new use case for ML tools: building new theory from quantitative observational data.
      LinkedIn
      Email

      Author Abstract

      We describe how to employ machine learning methods in theory development. Compared to traditional causal inference methods, ML methods make far fewer a priori assumptions about the functional form of the underlying model that best represents the data. Given this, researchers could use such methods to explore novel and robust patterns in the data that could lead to inductive theory building. ML strengths include replicable identification of novel patterns in the data. Additionally, ML methods address several concerns (such as “p-hacking” and confounding local effects for global effects) raised by scholars relative to the norms of empirical research in the fields of strategy and management. We develop a step-by-step roadmap that illustrates how to use four ML methods (decision trees, random forests, K-nearest neighbors, and neural networks) to reveal patterns in data that could be used for theory building. We also illustrate how ML methods could better illuminate interactions and non-linear effects, relative to traditional methods. In summary, ML methods could act as a complementary tool to both existing inductive theory-creating methods such as multiple case inductive studies and traditional methods of causal inference.

      Paper Information

      • Full Working Paper Text
      • Working Paper Publication Date: September 2018
      • HBS Working Paper Number: HBS Working Paper #19-032
      • Faculty Unit(s): Technology and Operations Management
      Post A Comment
      In order to be published, comments must be on-topic and civil in tone, with no name calling or personal attacks. Your comment may be edited for clarity and length.
        Trending
          • 29 Oct 2020
          • Research & Ideas

          The COVID Gender Gap: Why Fewer Women Are Dying

          • 13 Jul 2020
          • Research & Ideas

          Merck CEO Ken Frazier Discusses a COVID Cure, Racism, and Why Leaders Need to Walk the Talk

          • 25 Feb 2019
          • Research & Ideas

          How Gender Stereotypes Kill a Woman’s Self-Confidence

          • 19 Jan 2021
          • In Practice

          Leadership Advice for Biden: Restore a Sense of Calm

          • 01 Nov 2020
          • Research & Ideas

          Good Leadership Is an Act of Kindness

      Prithwiraj Choudhury
      Prithwiraj Choudhury
      Lumry Family Associate Professor of Business Administration
      Contact
      Send an email
      → More Articles
      Find Related Articles
      • Technology Adoption
      • Technological Innovation
      • Technology
      • Management Analysis, Tools, and Techniques
      • Theory

      Sign up for our weekly newsletter

      Interested in improving your business? Learn about fresh research and ideas from Harvard Business School faculty.
      ǁ
      Campus Map
      Harvard Business School Working Knowledge
      Baker Library | Bloomberg Center
      Soldiers Field
      Boston, MA 02163
      Email: Editor-in-Chief
      →Map & Directions
      →More Contact Information
      • Make a Gift
      • Site Map
      • Jobs
      • Harvard University
      • Trademarks
      • Policies
      • Digital Accessibility
      Copyright © President & Fellows of Harvard College